• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.350-352
• /
• 2000

위성이 보내어오는 영상의 량은 인간이 일일이 실시간으로 검색할 수 없을 정도의 방대한 양이다. 그러므로 위성이 보내어오는 영상을 자동적으로 빠른 시간내에 분석하기 위하여 원패스로 성질이 유사한 영역을 묶어서 분류하는 알고리즘이 필요하다. 본 연구에서는 자기조직화 신경망(SOM)을 인공위성 영상을 원패스에 분할할 수 있도록 학습방법을 개선하였으며 개선된 SOM 알고리즘이 같은 원패스 알고리즘인 온라인 K-means과 비교하여 유효함을 알 수 있었다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.5
• /
• pp.64-76
• /
• 2008

To increase road safety at blackspots, it is needed to develop a new method that can process before accident occurrence. Accident situation could result from traffic conflict. Traffic conflict decision technique has an advantage that can acquire and analyze data in time and confined space that is less through investigation. Therefore, traffic conflict technique is highly expected to be used in many application of road safety. This study developed traffic conflict decision program that can analyze and process from signalized intersection image. Program consists of the following functional modules: an image input module that acquires images from the CCTV camera, a Save-to-Buffer module which stores the entered images by differentiating them into background images, current images, difference images, segmentation images, and a conflict detection module which displays the processed results. The program was developed using LabVIEW 8.5 (a graphic language) and the VISION module library.

• Progress in Medical Physics
• /
• v.17 no.1
• /
• pp.24-31
• /
• 2006

Automated analysis software was developed to measure the magnitude of the intrafractional and interfractional errors during breast radiation treatments. Error analysis results are important for determining suitable planning target volumes (PTV) prior to Implementing breast-conserving 3-D conformal radiation treatment (CRT). The electrical portal imaging device (EPID) used for this study was a Portal Vision LC250 liquid-filled ionization detector (fast frame-averaging mode, 1.4 frames per second, 256X256 pixels). Twelve patients were imaged for a minimum of 7 treatment days. During each treatment day, an average of 8 to 9 images per field were acquired (dose rate of 400 MU/minute). We developed automated image analysis software to quantitatively analyze 2,931 images (encompassing 720 measurements). Standard deviations ($\sigma$) of intrafractional (breathing motion) and intefractional (setup uncertainty) errors were calculated. The PTV margin to include the clinical target volume (CTV) with 95% confidence level was calculated as $2\;(1.96\;{\sigma})$. To compensate for intra-fractional error (mainly due to breathing motion) the required PTV margin ranged from 2 mm to 4 mm. However, PTV margins compensating for intefractional error ranged from 7 mm to 31 mm. The total average error observed for 12 patients was 17 mm. The intefractional setup error ranged from 2 to 15 times larger than intrafractional errors associated with breathing motion. Prior to 3-D conformal radiation treatment or IMRT breast treatment, the magnitude of setup errors must be measured and properly incorporated into the PTV. To reduce large PTVs for breast IMRT or 3-D CRT, an image-guided system would be extremely valuable, if not required. EPID systems should incorporate automated analysis software as described in this report to process and take advantage of the large numbers of EPID images available for error analysis which will help Individual clinics arrive at an appropriate PTV for their practice. Such systems can also provide valuable patient monitoring information with minimal effort.

• 전자공학회논문지 IE
• /
• v.43 no.2
• /
• pp.39-48
• /
• 2006

This paper is proposed the wavelet morphology algorithm with the spatial auto-object segmentation concept and the clustering concept. When it is segmented the color face by using the proposed algorithm, it is made to the simple image. Also, it is used the spatial quality in order to segment and detect the image as a real time without the user's manufacturing. This removed a small part that is regarded as a noise in image by HSV color model and applied the wavelet morphology to remove a part excepting for the face image. In this paper, it is made a comparison between the wavelet morphology algorithm and the morphology algorithm. And It is showed to accurately detect the face object parts in the image appled to HSV color space model.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.209-214
• /
• 2004

국지적으로 단시간 내에 많은 양의 강한 비가 내리는 현상인 집중호우는 발생부터 성장, 쇠퇴까지의 과정이 단기간에 이루어지고, 그 변동성이 아주 크다. 그러므로 정확한 예보를 위해서는 단시간예보(nowcasting) 기법이 필요한데, 이를 위해서는 연속적이고, 정확한 관측이 필요하다. 집중호우의 관측에는 우량계, 레이다, 위성 관측 등이 사용되는데 이 연구에서는 GOES-9호 위성영상자료를 이용하였고, 2003년 여름의 8개 강수사례에 대해 분석하였다. 집중호우시의 강수량을 산출하기 위해 Power-law Curve를 사용하였고, NOAA/NESDIS에서 개발하여 현업에 사용 중인 Auto-Estimator의 무강수 픽셀 보정방법을 이용하여 산출된 강수량을 보정하였으며, 이를 기상청의 자동기상관측자료 (Automatic Weather Station: AWS)와 비교하였다. 위성영상자료의 시간 대표성을 분석하기 위해 위성의 관측 시간에 대해 전, 후, 중심을 기준으로 각각 15분, 30분, 60분 누적강수량과 비교하였고, AWS의 공간 대표성을 분석하기 위해 위성영상자료의 3×3, 5×5, 9×9 픽셀을 면적 평균하여 각각 비교하였다. 분석 결과 대부분의 사례에서 위성의 관측시간을 시작으로 60분 동안 누적한 강수량과 상관성이 가장 크게 나왔고, 면적에 대해서는 거의 차이가 없었다. 또한, 무강수 픽셀 보정방법의 하나로 구름의 성장률을 보정해 주었다. 그 결과 구름의 성장률을 보정해 주었을 때 상관계수가 0.05 이상 상승하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.535-538
• /
• 2022

근감소증은 영양부족, 운동량 감소 그리고 노화 등으로 정상적인 근육의 양과 근력 및 근 기능이 감소하는 질환을 말한다. 근감소증은 보편적으로 유럽 근감소증 실무그룹분석(EWGSOP)에서 정의한 측정 방법을 따른다. 본 논문에서는 근감소증 진단을 위한 영상 분할 모델을 개발하고 외부검증하는 방법에 대해서 제안한다. 우리는 CT 영상에서 L3 영역을 선별하여 자동으로 근육, 피하지방, 내장지방을 분할할 수 있는 인공지능 모델을 U-Net을 사용하여 개발하였다. 또한 모델의 성능을 평가하기 위해서 분할영역의 IOU(Intersection over Union)를 계산하여 내부검증을 진행하였으며, 타 병원의 데이터를 이용하여 같은 방법으로 외부검증을 진행한 결과를 보인다. 검증 결과를 토대로 문제점과 해결방안에 대해서 고찰하고 보완하고자 했다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.1
• /
• pp.17-31
• /
• 2002

The new MPEG-4 video coding standard enables content-based functionalities. Image segmentation is an indispensable process for it. This paper addresses an effective segmentation of non-rigid objects. Non-rigid objects are deformable objects with fuzzy, blurred and indefinite boundaries. So it is difficult to segment deformable objects precisely. In order to solve this problem, we propose an effective segmentation of non-rigid objects using watershed algorithms in still pictures. And we propose an automatic segmentation through intra-frame and inter-frame segmentation process in video sequences. Automatic segmentation preforms boundary-based and region-based segmentation to extract precise object boundaries.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.45-53
• /
• 2013

Global warming causes sea levels to rise and global changes apparently taking place including coastline changes. Coastline change due to sea level rise is also one of the most significant phenomena affected by global climate change. Accordingly, Coastline change detection can be utilized as an indicator of representing global climate change. Generally, Coastline change has happened mainly because of not only sea level rise but also artificial factor that is reclaimed land development by mud flat reclamation. However, Arctic coastal areas have been experienced serious change mostly due to sea level rise rather than other factors. The purposes of this study are automatic extraction of coastline and identifying change. In this study, in order to extract coastline automatically, contrast of the water and the land was maximized utilizing modified NDWI(Normalized Difference Water Index) and it made automatic extraction of coastline possibile. The imagery converted into modified NDWI were applied image processing techniques in order that appropriate threshold value can be found automatically to separate the water and land. Then the coastline was extracted through edge detection algorithm and changes were detected using extracted coastlines. Without the help of other data, automatic extraction of coastlines using LANDSAT was possible and similarity was found by comparing NLCD data as a reference data. Also, the results of the study area that is permafrost always frozen below $0^{\circ}C$ showed quantitative changes of the coastline and verified that the change was accelerated.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.4
• /
• pp.125-131
• /
• 2016

Tongue image segmentation is critical for automation of the tongue diagnosis system. However, most image segmentation methods for tongue diagnosis systems in oriental medicine have been proposed as user-based manual types or semi-automatic types. This study proposed a new method for tongue image segmentation, which is the most important image processing stage for complete automation of the tongue diagnosis system in oriental medicine. The proposed method improved the conventional snake algorithm, by making improvement on the internal energy function so that, as the points move outward reversely, the snake energy function is minimized, by using the image characteristics of tongue images. To calculate external energy, hierarchical spatial filtering is applied to ensure resistance against noise. Also, The proposed method was tested by using sample images and actual images, and showed more robustness against the background noise than the conventional snake algorithm. And, when one selected point was moved by the improved snake algorithm, energy values at the starting, middle, and end points were analyzed, and showed robustness that does not fall in the local minima.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.11b
• /
• pp.93-98
• /
• 1999

본 논문에서는 영상 내 존재하는 의미 있는 객체단위로 초상권을 보호하는 기법을 제안한다. 제안된 방법은 초상권 보호 객체선택 단계와 객체에 마스크를 적용하는 단계 그리고 마스크가 적용된 객체를 추적하는 단계로 나누어진다. 초상권 보호 객체선택 단계에서는 블록분류(block classification) 및 워터쉐드(watershed) 알고리듬을 이용하여 분할된 결과영상을 얻고 이를 이용하여 사용자가 원하는 객체를 마우스로 클릭함으로써 손쉽게 초상권 보호법을 적용시킬 객체를 추출할 수 있다. 이렇게 정의된 객체는 다음 단계에서 마스크를 적용 받게 된다. 첫 번째 프레임에서 마스크가 적용되면 다음 프레임부터는 객체추적과정에서 연된 화면사이의 움직임 및 밝기정보에 의해 객체를 추적, 계속 마스크를 적용함으로써 초상권을 보호할 수 있다. 제안된 알고리듬은 초상권 보호를 위한 모자이크 처리 시 화질 저하에 따른 시청자의 화면 거부감을 최소화시키고, 반자동영상분할 알고리듬을 사용하여 객체 단위로 초상권 마스크를 적용하여 초상권 보호대상물을 놓치지 않고 추적할 수 있어 신뢰도를 높일 수 있는 장점을 가지고 있다.